相关论文: A Compact End-to-End Model with Local and Global C…

Speech transcription, emotion recognition, and language identification are usually considered to be three different tasks. Each one requires a different model with a different architecture and training process. We propose using a recurrent…

Speaker identification systems in a real-world scenario are tasked to identify a speaker amongst a set of enrolled speakers given just a few samples for each enrolled speaker. This paper demonstrates the effectiveness of meta-learning and…

This paper introduces a novel framework for designing efficient neural network architectures specifically tailored to tiny machine learning (TinyML) platforms. By leveraging large language models (LLMs) for neural architecture search (NAS),…

The word-level lipreading approach typically employs a two-stage framework with separate frontend and backend architectures to model dynamic lip movements. Each component has been extensively studied, and in the backend architecture,…

End-to-end Task-Oriented Dialog (TOD) systems typically require extensive training datasets to perform well. In contrast, large language model (LLM) based TOD systems can excel even with limited data due to their ability to learn tasks…

Strong presentation skills are valuable and sought-after in workplace and classroom environments alike. Of the possible improvements to vocal presentations, disfluencies and stutters in particular remain one of the most common and prominent…

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these…

The text-based speech editor allows the editing of speech through intuitive cutting, copying, and pasting operations to speed up the process of editing speech. However, the major drawback of current systems is that edited speech often…

Recent studies on dense captioning and visual grounding in 3D have achieved impressive results. Despite developments in both areas, the limited amount of available 3D vision-language data causes overfitting issues for 3D visual grounding…

Vehicle re-identification (Re-ID) is a crucial task in intelligent transportation systems (ITS), aimed at retrieving and matching the same vehicle across different surveillance cameras. Numerous studies have explored methods to enhance…

Traditional Time Delay Neural Networks (TDNN) have achieved state-of-the-art performance at the cost of high computational complexity and slower inference speed, making them difficult to implement in an industrial environment. The Densely…

Accurate and fast scene understanding is one of the challenging task for autonomous driving, which requires to take full advantage of LiDAR point clouds for semantic segmentation. In this paper, we present a \textbf{concise} and…

Fine-tuning pretrained language models (LMs) without making any architectural changes has become a norm for learning various language downstream tasks. However, for non-language downstream tasks, a common practice is to employ task-specific…

Artificial intelligence has achieved notable results in sign language recognition and translation. However, relatively few efforts have been made to significantly improve the quality of life for the 72 million hearing-impaired people…

Robust local feature representations are essential for spatial intelligence tasks such as robot navigation and augmented reality. Establishing reliable correspondences requires descriptors that provide both high discriminative power and…

Lip motion reflects behavior characteristics of speakers, and thus can be used as a new kind of biometrics in speaker recognition. In the literature, lots of works used two-dimensional (2D) lip images to recognize speaker in a textdependent…

We train and deploy a quantized 1D convolutional neural network model to conduct speech recognition on a highly resource-constrained IoT edge device. This can be useful in various Internet of Things (IoT) applications, such as smart homes…

We propose Citrinet - a new end-to-end convolutional Connectionist Temporal Classification (CTC) based automatic speech recognition (ASR) model. Citrinet is deep residual neural model which uses 1D time-channel separable convolutions…

Vision-language models (VLMs) such as CLIP exhibit strong Out-of-distribution (OOD) detection capabilities by aligning visual and textual representations. Recent CLIP-based test-time adaptation methods further improve detection performance…

This technical report describes the IDLab submission for track 1 and 2 of the VoxCeleb Speaker Recognition Challenge 2021 (VoxSRC-21). This speaker verification competition focuses on short duration test recordings and cross-lingual trials.…